Neural Networks,Decision Tree Induction and Discriminant Analysis: an Empirical Comparison

This paper presents an empirical comparison of three classification methods: neural networks, decision tree induction and linear discriminant analysis. The comparison is based on seven datasets with different characteristics, four being real, and three artificially created. Analysis of variance was used to detect any significant differences between the performance of the methods. There is also some discussion of the problems involved with using neural networks and, in particular, on overfitting of the training data. A comparison between two methods to prevent overfitting is presented: finding the most appropriate network size, and the use of an independent validation set to determine when to stop training the network.     

A Comparison of Data Envelopment Analysis and Artificial Neural Networks as Tools for Assessing the Efficiency of Decision Making Units

This paper is concerned with the comparison of two popular non-parametric methodologies—data envelopment analysis and artificial neural networks—as tools for assessing performance. Data envelopment analysis has been established since 1978 as a superior alternative to traditional parametric methodologies, such as regression analysis, for assessing performance. Neural networks have recently been proposed as a method for assessing performance. In this paper, we use a simulated production technology of two inputs and one output for testing the success of the two methods for assessing efficiency. The two methods are also compared on their practical use as performance measurement tools on a set of bank branches, having multiple input and output criteria. The results demonstrate that, despite their differences, both methods offer a useful range of information regarding the assessment of performance.     

Decision Analysis

Journal of the Operational Research Society -     

星可数网和局部S可数网

The concept of local s-countablity is introduced, and the relations between locally s-countable collections and star-countable collections are discussed.     

协调决策理论及其智能化决策支持系统

本文针对多因素决策问题 ,建立了一种多专家协调决策的理论、方法、计算过程和应用实例 .设计了相应的智能化计算机决策支持系统 .     

向量值马氏决策规划的线性加权解法

类似［１－４］,折扣向量值马氏决策规划（ＤＶＭＤＰ）描述为： ｛Ｓ,（Ａ（ｉ）,ｉ∈Ｓ）,ｑ,ｒ,Ｖβ｝,（１）其中Ｓ为可数状态集,Ａ（ｉ）是有限决策集,ｑ（ｊ｜ｉ,ａ）是转移概率,ｒ＝ｒ（ｉ,ｊ,ａ）＝（ｒ１（ｉ,ｊ,ａ）,ｒ２（ｉ,ｊ,ａ）,…,ｒｐ（ｉ,ｊ,ａ））是状态ｉ处使用决策ａ于下一步转移到状态ｊ时所获的ｐ维报酬向量,ｒ（ｉ,ｊ,ａ）对ｉ,ｊ,ａ一致有界,Ｖβ是β折扣目标． 以Π表一般策略集,若　π　∈Π有 Ｖβ（π）≤ Ｖβ（π*）,则称π* 为ＤＶＭＤＰ的“强有效策略”,Ｖβ（π*）为“…     

Subjective Aspects of the Art of Decision Analysis: Exploring the Role of Decision Analysis in Decision Structuring,Decision Support and Policy Dialogue

The paper argues that, until very recently, decision analysts have devoted relatively little attention to the processes of problem formulation and subjective judgement in handling ill-structured strategic decision problems. Therefore, following a brief review of existing varieties of decision analysis, a modified policy dialogue' model of decision analysis is presented which integrates decision analysis with decision aids and decision support technology. This model is developed using as an illustration strategic problems drawn from the insurance industry. The paper concludes with some suggestions for the successful application and implementation of decision analysis.     

对换网络和乘积循环网络的超连通性

本文证明了对换网络和乘积循环网络是超连通的。     

Inquiry and Decision

Journal of the Operational Research Society -